© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 42189
    Prev
    Next
    INDEX
    Explanations

    periods and statements or clauses that indicate completion or end of thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    non-English words and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uParam
    -0.39
    《
    -0.37
    Биография
    -0.37
     menem
    -0.36
     pan
    -0.36
     the
    -0.34
    apuram
    -0.33
     auctions
    -0.33
    Läs
    -0.33
    「
    -0.32
    POSITIVE LOGITS
    lapsingToolbar
    0.66
     kasarigan
    0.66
    AddTagHelper
    0.64
    richTextPanel
    0.60
    AnimationsModule
    0.59
     <<<<<<<<<<<<<<
    0.59
     Италијани
    0.59
    optionalTypeArgs
    0.58
     okuyayım
    0.58
     gynhyrchwyd
    0.56
    Activations Density 0.105%

    No Known Activations